library(tidyverse)
library(tidyLPA)
library(dplyr)
library(kableExtra)Latent Profile Analysis
Research Question: What combinations of self-efficacy levels, persistence levels, statistics anxiety, and statistics grades exist?
Data Prep
#read in data
smarvus_data <- here::here("docs/SMARVUS_projects/SMARVUS_dissertations.csv") |> readr::read_csv()
#selecting variables
smarvus_data <- smarvus_data |>
dplyr::select(
country, university, eligibility_stats, degree_major, degree_year, age, gender, attention_amnesty, Q7.1_1:Q7.1_24, Q15.1_1:Q15.1_9, Q16.1_1:Q16.1_7, stats_edu_first_module, stats_edu_module_1, grading_scale, grade
)
##attention checks
#how many people failed attention amnesty
attention_amnesty_exclusion <- smarvus_data |>
dplyr::filter(attention_amnesty == "No" | is.na(attention_amnesty)) |>
nrow()
#how many poeple failed the statistics anxiety attention check
anxiety_attention_exclusion <- smarvus_data |>
dplyr::filter(Q7.1_24 != "1" | is.na(Q7.1_24)) |>
nrow()
#how many people failed the self-efficacy attention check
se_attention_exclusion <- smarvus_data |>
dplyr::filter(Q15.1_9 != "4" | is.na(Q15.1_9)) |>
nrow()
##eligibility exclusions
#how many poeple failed stats eligibility question
non_stats_exclusion <- smarvus_data |>
dplyr::filter(eligibility_stats == "No" | is.na(eligibility_stats)) |>
nrow()
#removing exclusions
smarvus_data_exclusions <- smarvus_data |>
dplyr::filter(
attention_amnesty == "Yes",
Q7.1_24 == "1",
Q15.1_9 == "4",
eligibility_stats == "Yes"
)
#removing those without grade data
smarvus_data_exclusions <- smarvus_data_exclusions |> dplyr::filter(!is.na(grade))
#selecting those with grade data on the scale 0-100
smarvus_data_exclusions <- smarvus_data_exclusions |>
filter(
university == "Anglia Ruskin University" |
university == "Bournemouth University" |
university == "Macquarie University" |
university == "Queen's University Belfast" |
university == "Teesside University" |
university == "University of Bradford" |
university == "University of Lincoln" |
university == "University of Southampton" |
university == "University of Sussex" |
university == "University of Western Australia"
)
#turn grade data into numerical values
smarvus_data_exclusions$grade <- parse_number(smarvus_data_exclusions$grade)Participant Summaries
#age
n_age <- smarvus_data_exclusions |>
group_by(age) |>
summarise(n = n()) |>
mutate(percentage = (n / sum(n)) *100)
n_age# A tibble: 4 × 3
age n percentage
<chr> <int> <dbl>
1 18-21 731 85.6
2 22-25 64 7.49
3 26+ 54 6.32
4 <NA> 5 0.585#gender
n_gender <- smarvus_data_exclusions |>
group_by(gender) |>
summarise(n = n()) |>
mutate(percentage = (n / sum(n)) *100)
n_gender# A tibble: 4 × 3
gender n percentage
<chr> <int> <dbl>
1 Another Gender 10 1.17
2 Female/Woman 717 84.0
3 Male/Man 126 14.8
4 <NA> 1 0.117#country
n_country <- smarvus_data_exclusions |>
group_by(country) |>
summarise(n = n()) |>
mutate(percentage = (n / sum(n)) *100)
n_country# A tibble: 3 × 3
country n percentage
<chr> <int> <dbl>
1 Australia 29 3.40
2 England 733 85.8
3 Northern Ireland 92 10.8 #degree major
n_major <- smarvus_data_exclusions |>
group_by(degree_major) |>
summarise(n = n()) |>
mutate(percentage = (n / sum(n)) *100)
n_major# A tibble: 5 × 3
degree_major n percentage
<chr> <int> <dbl>
1 Education 1 0.117
2 Psychology 842 98.6
3 Sciences 2 0.234
4 Social Sciences 6 0.703
5 <NA> 3 0.351#degree year
n_year <- smarvus_data_exclusions |>
group_by(degree_year) |>
summarise(n = n()) |>
mutate(percentage = (n / sum(n)) *100)
n_year# A tibble: 4 × 3
degree_year n percentage
<chr> <int> <dbl>
1 1st Year 530 62.1
2 2nd Year 303 35.5
3 3rd Year 19 2.22
4 4th Year 2 0.234#university
n_uni <- smarvus_data_exclusions |>
group_by(university) |>
summarise(n = n()) |>
mutate(percentage = (n / sum(n)) *100)
n_uni# A tibble: 10 × 3
university n percentage
<chr> <int> <dbl>
1 Anglia Ruskin University 16 1.87
2 Bournemouth University 176 20.6
3 Macquarie University 6 0.703
4 Queen's University Belfast 92 10.8
5 Teesside University 31 3.63
6 University of Bradford 30 3.51
7 University of Lincoln 63 7.38
8 University of Southampton 83 9.72
9 University of Sussex 334 39.1
10 University of Western Australia 23 2.69 #first statistics module
n_first <- smarvus_data_exclusions |>
group_by(stats_edu_first_module) |>
summarise(n = n()) |>
mutate(percentage = (n / sum(n)) *100)
n_first# A tibble: 3 × 3
stats_edu_first_module n percentage
<chr> <int> <dbl>
1 No 213 24.9
2 Yes 244 28.6
3 <NA> 397 46.5Composite Scores
#recode reverse scored items
composite_data <- smarvus_data_exclusions %>%
mutate(Q16.1_2 = 6-Q16.1_2,
Q16.1_3 = 6-Q16.1_3,
Q16.1_4 = 6-Q16.1_4,
Q16.1_5 = 6-Q16.1_5,
Q16.1_7 = 6-Q16.1_7)
#statistics anxiety
composite_data <- composite_data %>%
mutate(statistics_anxiety = rowMeans(select(., Q7.1_1:Q7.1_23), na.rm = TRUE))
#self-efficacy
composite_data <- composite_data %>%
mutate(self_efficacy = rowMeans(select(., Q15.1_1:Q15.1_8), na.rm = TRUE))
#persistence
composite_data <- composite_data %>%
mutate(persistence = rowMeans(select(., Q16.1_1:Q16.1_7), na.rm = TRUE))
data <- composite_data %>%
select(self_efficacy, statistics_anxiety, persistence, grade)Latent Profile Analysis
Fit statistics
lpa_mod <- data %>%
dplyr::select(self_efficacy, statistics_anxiety, persistence, grade) %>%
scale() %>%
tidyLPA::single_imputation(method = "missForest") %>%
tidyLPA::estimate_profiles(1:6) %>%
tidyLPA::get_fit()
lpa_mod# A tibble: 6 × 18
Model Classes LogLik AIC AWE BIC CAIC CLC KIC SABIC ICL Entropy
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 1 1 -4845. 9706. 9820. 9744. 9752. 9692. 9717. 9719. -9744. 1
2 1 2 -4747. 9519. 9706. 9581. 9594. 9494. 9535. 9539. -9871. 0.538
3 1 3 -4691. 9417. 9677. 9503. 9521. 9383. 9438. 9446. -9804. 0.698
4 1 4 -4679. 9403. 9736. 9512. 9535. 9358. 9429. 9439. -10095. 0.562
5 1 5 -4675. 9406. 9811. 9539. 9567. 9351. 9437. 9450. -10371. 0.493
6 1 6 -4666. 9399. 9876. 9555. 9588. 9334. 9435. 9451. -10447. 0.495
# ℹ 6 more variables: prob_min <dbl>, prob_max <dbl>, n_min <dbl>, n_max <dbl>,
# BLRT_val <dbl>, BLRT_p <dbl>#formatted table
lpa_mod %>%
select(Classes, AIC, BIC, SABIC, Entropy, n_min, BLRT_p) %>%
kable(
digits = 4,
col.names = c("Profiles", "AIC", "BIC", "SABIC", "Entropy", "N(Min)", "BLRT(p)")
) %>%
kableExtra::kable_styling()| Profiles | AIC | BIC | SABIC | Entropy | N(Min) | BLRT(p) |
|---|---|---|---|---|---|---|
| 1 | 9706.186 | 9744.185 | 9718.779 | 1.0000 | 1.0000 | NA |
| 2 | 9519.031 | 9580.780 | 9539.496 | 0.5378 | 0.3888 | 0.0099 |
| 3 | 9417.423 | 9502.922 | 9445.759 | 0.6982 | 0.0164 | 0.0099 |
| 4 | 9403.198 | 9512.447 | 9439.405 | 0.5619 | 0.0152 | 0.0099 |
| 5 | 9405.822 | 9538.820 | 9449.900 | 0.4931 | 0.0152 | 0.2178 |
| 6 | 9398.681 | 9555.428 | 9450.630 | 0.4952 | 0.0152 | 0.0396 |
Estimating profiles
#plots and estimates for 2-6 profile solutions
#estimating 2 profiles
lpa_2 <- data %>%
dplyr::select(self_efficacy, statistics_anxiety, persistence, grade) %>%
scale() %>%
tidyLPA::single_imputation(method = "missForest") %>%
tidyLPA::estimate_profiles(2)
lpa_2tidyLPA analysis using mclust:
Model Classes AIC BIC Entropy prob_min prob_max n_min n_max BLRT_p
1 2 9519.03 9580.78 0.54 0.80 0.90 0.39 0.61 0.01 tidyLPA::plot_profiles(lpa_2)
tidyLPA::get_estimates(lpa_2)# A tibble: 16 × 8
Category Parameter Estimate se p Class Model Classes
<chr> <chr> <dbl> <dbl> <dbl> <int> <dbl> <dbl>
1 Means self_efficacy -0.449 0.168 7.41e- 3 1 1 2
2 Means statistics_anxiety 0.468 0.0702 2.70e-11 1 1 2
3 Means persistence -0.783 0.0972 8.01e-16 1 1 2
4 Means grade -0.315 0.330 3.39e- 1 1 1 2
5 Variances self_efficacy 0.858 0.0544 4.88e-56 1 1 2
6 Variances statistics_anxiety 0.847 0.0441 3.00e-82 1 1 2
7 Variances persistence 0.573 0.0537 1.41e-26 1 1 2
8 Variances grade 0.930 0.0769 1.16e-33 1 1 2
9 Means self_efficacy 0.312 0.0632 7.81e- 7 2 1 2
10 Means statistics_anxiety -0.325 0.0675 1.46e- 6 2 1 2
11 Means persistence 0.544 0.0764 1.05e-12 2 1 2
12 Means grade 0.219 0.0449 1.03e- 6 2 1 2
13 Variances self_efficacy 0.858 0.0544 4.88e-56 2 1 2
14 Variances statistics_anxiety 0.847 0.0441 3.00e-82 2 1 2
15 Variances persistence 0.573 0.0537 1.41e-26 2 1 2
16 Variances grade 0.930 0.0769 1.16e-33 2 1 2#estimating 3 profiles
lpa_3 <- data %>%
dplyr::select(self_efficacy, statistics_anxiety, persistence, grade) %>%
scale() %>%
tidyLPA::single_imputation(method = "missForest") %>%
tidyLPA::estimate_profiles(3)
lpa_3tidyLPA analysis using mclust:
Model Classes AIC BIC Entropy prob_min prob_max n_min n_max BLRT_p
1 3 9417.42 9502.92 0.70 0.80 0.92 0.02 0.59 0.01 tidyLPA::plot_profiles(lpa_3)
tidyLPA::get_estimates(lpa_3)# A tibble: 24 × 8
Category Parameter Estimate se p Class Model Classes
<chr> <chr> <dbl> <dbl> <dbl> <int> <dbl> <dbl>
1 Means self_efficacy -0.400 0.0677 3.41e- 9 1 1 3
2 Means statistics_anxiety 0.436 0.0717 1.26e- 9 1 1 3
3 Means persistence -0.758 0.0820 2.52e-20 1 1 3
4 Means grade -0.177 0.0539 1.02e- 3 1 1 3
5 Variances self_efficacy 0.851 0.0502 2.10e-64 1 1 3
6 Variances statistics_anxiety 0.846 0.0499 1.64e-64 1 1 3
7 Variances persistence 0.565 0.0460 1.02e-34 1 1 3
8 Variances grade 0.743 0.0521 3.97e-46 1 1 3
9 Means self_efficacy 0.315 0.0513 7.91e-10 2 1 3
10 Means statistics_anxiety -0.330 0.0867 1.41e- 4 2 1 3
# ℹ 14 more rows#estimating 4 profiles
lpa_4 <- data %>%
dplyr::select(self_efficacy, statistics_anxiety, persistence, grade) %>%
scale() %>%
tidyLPA::single_imputation(method = "missForest") %>%
tidyLPA::estimate_profiles(4)
lpa_4tidyLPA analysis using mclust:
Model Classes AIC BIC Entropy prob_min prob_max n_min n_max BLRT_p
1 4 9403.20 9512.45 0.56 0.58 0.90 0.02 0.54 0.02 tidyLPA::plot_profiles(lpa_4)
tidyLPA::get_estimates(lpa_4)# A tibble: 32 × 8
Category Parameter Estimate se p Class Model Classes
<chr> <chr> <dbl> <dbl> <dbl> <int> <dbl> <dbl>
1 Means self_efficacy -0.503 0.195 9.74e- 3 1 1 4
2 Means statistics_anxiety 0.455 0.0798 1.21e- 8 1 1 4
3 Means persistence -0.945 0.0937 6.58e-24 1 1 4
4 Means grade -0.204 0.0894 2.26e- 2 1 1 4
5 Variances self_efficacy 0.827 0.0579 2.52e-46 1 1 4
6 Variances statistics_anxiety 0.771 0.0688 3.37e-29 1 1 4
7 Variances persistence 0.534 0.0544 9.50e-23 1 1 4
8 Variances grade 0.733 0.0543 1.52e-41 1 1 4
9 Means self_efficacy 0.567 0.243 1.97e- 2 2 1 4
10 Means statistics_anxiety -0.850 0.178 1.70e- 6 2 1 4
# ℹ 22 more rows#estimating 5 profiles
lpa_5 <- data %>%
dplyr::select(self_efficacy, statistics_anxiety, persistence, grade) %>%
scale() %>%
tidyLPA::single_imputation(method = "missForest") %>%
tidyLPA::estimate_profiles(5)
lpa_5tidyLPA analysis using mclust:
Model Classes AIC BIC Entropy prob_min prob_max n_min n_max BLRT_p
1 5 9405.82 9538.82 0.49 0.49 0.89 0.02 0.37 0.19 tidyLPA::plot_profiles(lpa_5)
tidyLPA::get_estimates(lpa_5)# A tibble: 40 × 8
Category Parameter Estimate se p Class Model Classes
<chr> <chr> <dbl> <dbl> <dbl> <int> <dbl> <dbl>
1 Means self_efficacy -0.569 0.379 1.34e- 1 1 1 5
2 Means statistics_anxiety 0.473 0.116 4.32e- 5 1 1 5
3 Means persistence -0.959 0.152 2.61e-10 1 1 5
4 Means grade -0.169 0.131 1.97e- 1 1 1 5
5 Variances self_efficacy 0.771 0.127 1.34e- 9 1 1 5
6 Variances statistics_anxiety 0.802 0.0957 5.27e-17 1 1 5
7 Variances persistence 0.519 0.0878 3.34e- 9 1 1 5
8 Variances grade 0.693 0.0570 5.72e-34 1 1 5
9 Means self_efficacy -0.00743 0.594 9.90e- 1 2 1 5
10 Means statistics_anxiety -0.171 0.354 6.29e- 1 2 1 5
# ℹ 30 more rows#estimating 6 profiles
lpa_6 <- data %>%
dplyr::select(self_efficacy, statistics_anxiety, persistence, grade) %>%
scale() %>%
tidyLPA::single_imputation(method = "missForest") %>%
tidyLPA::estimate_profiles(6)
lpa_6tidyLPA analysis using mclust:
Model Classes AIC BIC Entropy prob_min prob_max n_min n_max BLRT_p
1 6 9398.68 9555.43 0.50 0.49 0.91 0.02 0.43 0.02 tidyLPA::plot_profiles(lpa_6)
tidyLPA::get_estimates(lpa_6)# A tibble: 48 × 8
Category Parameter Estimate se p Class Model Classes
<chr> <chr> <dbl> <dbl> <dbl> <int> <dbl> <dbl>
1 Means self_efficacy 0.107 0.326 7.42e- 1 1 1 6
2 Means statistics_anxiety 0.515 0.163 1.55e- 3 1 1 6
3 Means persistence -0.894 0.216 3.42e- 5 1 1 6
4 Means grade -0.215 0.103 3.72e- 2 1 1 6
5 Variances self_efficacy 0.571 0.0929 8.01e-10 1 1 6
6 Variances statistics_anxiety 0.799 0.0887 2.02e-19 1 1 6
7 Variances persistence 0.551 0.0744 1.26e-13 1 1 6
8 Variances grade 0.696 0.0648 6.31e-27 1 1 6
9 Means self_efficacy -0.0853 0.797 9.15e- 1 2 1 6
10 Means statistics_anxiety -0.206 0.433 6.33e- 1 2 1 6
# ℹ 38 more rowsDifferent Covariance Structures
#model 1: variances equal, covariances zero
mod1 <- data %>%
dplyr::select(self_efficacy, statistics_anxiety, persistence, grade) %>%
scale() %>%
tidyLPA::single_imputation(method = "missForest") %>%
tidyLPA::estimate_profiles(3)
tidyLPA::plot_profiles(mod1)
#model 2: variances varying, covariances zero
mod2 <- data %>%
dplyr::select(self_efficacy, statistics_anxiety, persistence, grade) %>%
scale() %>%
tidyLPA::single_imputation(method = "missForest") %>%
tidyLPA::estimate_profiles(3, variances = "varying", covariances = "zero")
tidyLPA::plot_profiles(mod2)
#model 3: equal variances, equal covariances
mod3 <- data %>%
dplyr::select(self_efficacy, statistics_anxiety, persistence, grade) %>%
scale() %>%
tidyLPA::single_imputation(method = "missForest") %>%
tidyLPA::estimate_profiles(3, variances = "equal", covariances = "equal")
tidyLPA::plot_profiles(mod3)
#model 6: varying variances, varying covariances
mod6 <- data %>%
dplyr::select(self_efficacy, statistics_anxiety, persistence, grade) %>%
scale() %>%
tidyLPA::single_imputation(method = "missForest") %>%
tidyLPA::estimate_profiles(3, variances = "varying", covariances = "varying")
tidyLPA::plot_profiles(mod6)
#comparing models
mod_table <- data %>%
dplyr::select(self_efficacy, statistics_anxiety, persistence, grade) %>%
scale() %>%
tidyLPA::single_imputation(method = "missForest") %>%
tidyLPA::estimate_profiles(3, models = c(1,2,3,6))
mod_tabletidyLPA analysis using mclust:
Model Classes AIC BIC Entropy prob_min prob_max n_min n_max BLRT_p
1 3 9417.42 9502.92 0.70 0.80 0.92 0.02 0.59 0.01
2 3 9363.15 9486.65 0.57 0.67 0.87 0.20 0.55 0.01
3 3 9385.31 9499.31 0.60 0.65 0.88 0.04 0.67 0.01
6 3 9304.35 9513.35 0.50 0.45 0.86 0.10 0.68 0.01 get_fit(mod_table)# A tibble: 4 × 18
Model Classes LogLik AIC AWE BIC CAIC CLC KIC SABIC ICL Entropy
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 1 3 -4691. 9417. 9677. 9503. 9521. 9383. 9438. 9446. -9804. 0.698
2 2 3 -4656. 9363. 9739. 9487. 9513. 9312. 9392. 9404. -9920. 0.566
3 3 3 -4669. 9385. 9732. 9499. 9523. 9339. 9412. 9423. -9912. 0.602
4 6 3 -4608. 9304. 9941. 9513. 9557. 9217. 9351. 9374. -10042. 0.502
# ℹ 6 more variables: prob_min <dbl>, prob_max <dbl>, n_min <dbl>, n_max <dbl>,
# BLRT_val <dbl>, BLRT_p <dbl>plot_profiles(mod_table, ci = NULL)
#formatted table
mod_table %>%
get_fit() %>%
select(Model, AIC, BIC, SABIC, Entropy, n_min, BLRT_p) %>%
kable(
digits = 4,
col.names = c("Model", "AIC", "BIC", "SABIC", "Entropy", "N(Min)", "BLRT(p)")
) %>%
kableExtra::kable_styling()| Model | AIC | BIC | SABIC | Entropy | N(Min) | BLRT(p) |
|---|---|---|---|---|---|---|
| 1 | 9417.423 | 9502.922 | 9445.759 | 0.6982 | 0.0164 | 0.0099 |
| 2 | 9363.149 | 9486.647 | 9404.079 | 0.5663 | 0.1956 | 0.0099 |
| 3 | 9385.311 | 9499.309 | 9423.092 | 0.6021 | 0.0363 | 0.0099 |
| 6 | 9304.348 | 9513.345 | 9373.614 | 0.5023 | 0.0995 | 0.0099 |
#retained model
get_estimates(mod2)# A tibble: 24 × 8
Category Parameter Estimate se p Class Model Classes
<chr> <chr> <dbl> <dbl> <dbl> <int> <dbl> <dbl>
1 Means self_efficacy -0.0614 0.124 6.20e- 1 1 2 3
2 Means statistics_anxiety 0.305 0.102 2.64e- 3 1 2 3
3 Means persistence -0.447 0.119 1.82e- 4 1 2 3
4 Means grade -0.0527 0.0295 7.39e- 2 1 2 3
5 Variances self_efficacy 0.661 0.151 1.26e- 5 1 2 3
6 Variances statistics_anxiety 0.651 0.0998 7.09e-11 1 2 3
7 Variances persistence 0.918 0.144 2.08e-10 1 2 3
8 Variances grade 0.0409 0.0124 9.60e- 4 1 2 3
9 Means self_efficacy 0.352 0.0689 3.22e- 7 2 2 3
10 Means statistics_anxiety -0.378 0.0685 3.40e- 8 2 2 3
# ℹ 14 more rows#calculating the size of each profile
profile <- get_data(mod2)
profile# A tibble: 854 × 10
model_number classes_number self_efficacy statistics_anxiety persistence
<dbl> <dbl> <dbl> <dbl> <dbl>
1 2 3 -0.622 1.04 0.0239
2 2 3 -0.433 -0.000907 -1.06
3 2 3 -0.243 -0.111 1.11
4 2 3 -1.38 -0.165 -1.93
5 2 3 -2.14 2.36 -1.06
6 2 3 0.892 1.97 -0.845
7 2 3 2.41 -1.92 0.893
8 2 3 1.65 0.273 -1.71
9 2 3 0.135 1.70 -0.845
10 2 3 -0.0541 -0.220 0.459
# ℹ 844 more rows
# ℹ 5 more variables: grade <dbl>, CPROB1 <dbl>, CPROB2 <dbl>, CPROB3 <dbl>,
# Class <dbl>profile_data <- data
profile_data$mod2_profile <- profile$Class
profile_data# A tibble: 854 × 5
self_efficacy statistics_anxiety persistence grade mod2_profile
<dbl> <dbl> <dbl> <dbl> <dbl>
1 3 3.91 3.43 66 1
2 3.12 3.09 2.71 84 3
3 3.25 3 4.14 70 2
4 2.5 2.96 2.14 88 3
5 2 4.96 2.71 15 3
6 4 4.65 2.86 82 3
7 5 1.57 4 82 2
8 4.5 3.30 2.29 67 1
9 3.5 4.43 2.86 76 3
10 3.38 2.91 3.71 62 2
# ℹ 844 more rowscount(profile_data, vars = mod2_profile)# A tibble: 3 × 2
vars n
<dbl> <int>
1 1 214
2 2 473
3 3 167Descriptive Statistics
Means and Standard Deviations
descriptives <- profile_data %>%
dplyr::group_by(mod2_profile) %>%
dplyr::summarise(
se_mean = mean(self_efficacy),
se_sd = sd(self_efficacy),
sa_mean = mean(statistics_anxiety),
sa_sd = sd(statistics_anxiety),
p_mean = mean(persistence),
p_sd = sd(persistence),
g_mean = mean(grade),
g_sd = sd(grade)
)
descriptives %>%
kable() %>%
kableExtra::kable_styling()| mod2_profile | se_mean | se_sd | sa_mean | sa_sd | p_mean | p_sd | g_mean | g_sd |
|---|---|---|---|---|---|---|---|---|
| 1 | 3.313084 | 0.5155658 | 3.408980 | 0.5991556 | 3.033378 | 0.5585674 | 65.34607 | 1.970737 |
| 2 | 3.674947 | 0.5399640 | 2.764918 | 0.7498583 | 3.793718 | 0.4724677 | 68.87455 | 10.421018 |
| 3 | 2.787425 | 0.6845865 | 3.590104 | 0.7006161 | 2.820359 | 0.4830452 | 58.34844 | 16.905470 |
Correlations
#correlation coefficients within each profile
profile_data %>%
filter(mod2_profile == 1) %>%
select(self_efficacy, statistics_anxiety, persistence, grade) %>%
cor(method="pearson") %>%
kable() %>%
kable_styling()| self_efficacy | statistics_anxiety | persistence | grade | |
|---|---|---|---|---|
| self_efficacy | 1.0000000 | 0.1213468 | -0.1549441 | -0.0448416 |
| statistics_anxiety | 0.1213468 | 1.0000000 | 0.1216082 | -0.0589335 |
| persistence | -0.1549441 | 0.1216082 | 1.0000000 | 0.0390405 |
| grade | -0.0448416 | -0.0589335 | 0.0390405 | 1.0000000 |
profile_data %>%
filter(mod2_profile == 2) %>%
select(self_efficacy, statistics_anxiety, persistence, grade) %>%
cor(method="pearson")%>%
kable() %>%
kable_styling()| self_efficacy | statistics_anxiety | persistence | grade | |
|---|---|---|---|---|
| self_efficacy | 1.0000000 | -0.0736568 | 0.0591574 | -0.1250761 |
| statistics_anxiety | -0.0736568 | 1.0000000 | -0.0006716 | -0.0073337 |
| persistence | 0.0591574 | -0.0006716 | 1.0000000 | 0.0778946 |
| grade | -0.1250761 | -0.0073337 | 0.0778946 | 1.0000000 |
profile_data %>%
filter(mod2_profile == 3) %>%
select(self_efficacy, statistics_anxiety, persistence, grade) %>%
cor(method="pearson")%>%
kable() %>%
kable_styling()| self_efficacy | statistics_anxiety | persistence | grade | |
|---|---|---|---|---|
| self_efficacy | 1.0000000 | 0.0918541 | -0.0491616 | -0.1646897 |
| statistics_anxiety | 0.0918541 | 1.0000000 | -0.0615996 | -0.0445675 |
| persistence | -0.0491616 | -0.0615996 | 1.0000000 | -0.0016742 |
| grade | -0.1646897 | -0.0445675 | -0.0016742 | 1.0000000 |
#correlation coefficients within the full sample
profile_data %>%
select(self_efficacy, statistics_anxiety, persistence, grade) %>%
cor(method="pearson")%>%
kable() %>%
kable_styling()| self_efficacy | statistics_anxiety | persistence | grade | |
|---|---|---|---|---|
| self_efficacy | 1.0000000 | -0.2195859 | 0.3028001 | 0.0787260 |
| statistics_anxiety | -0.2195859 | 1.0000000 | -0.2896573 | -0.1609535 |
| persistence | 0.3028001 | -0.2896573 | 1.0000000 | 0.2345787 |
| grade | 0.0787260 | -0.1609535 | 0.2345787 | 1.0000000 |
#correlation plots
profile_data %>%
filter(mod2_profile == 1) %>%
select(self_efficacy, statistics_anxiety, persistence, grade) %>%
GGally::ggscatmat()
profile_data %>%
filter(mod2_profile == 2) %>%
select(self_efficacy, statistics_anxiety, persistence, grade) %>%
GGally::ggscatmat()
profile_data %>%
filter(mod2_profile == 3) %>%
select(self_efficacy, statistics_anxiety, persistence, grade) %>%
GGally::ggscatmat()
profile_data %>%
select(self_efficacy, statistics_anxiety, persistence, grade) %>%
GGally::ggscatmat()
#significance of correlations
profile_data %>%
filter(mod2_profile == 1) %>%
select(self_efficacy, statistics_anxiety, persistence, grade) %>%
as.matrix() %>%
Hmisc::rcorr(type = "pearson") self_efficacy statistics_anxiety persistence grade
self_efficacy 1.00 0.12 -0.15 -0.04
statistics_anxiety 0.12 1.00 0.12 -0.06
persistence -0.15 0.12 1.00 0.04
grade -0.04 -0.06 0.04 1.00
n= 214
P
self_efficacy statistics_anxiety persistence grade
self_efficacy 0.0765 0.0234 0.5141
statistics_anxiety 0.0765 0.0759 0.3910
persistence 0.0234 0.0759 0.5700
grade 0.5141 0.3910 0.5700 profile_data %>%
filter(mod2_profile == 2) %>%
select(self_efficacy, statistics_anxiety, persistence, grade) %>%
as.matrix() %>%
Hmisc::rcorr(type = "pearson") self_efficacy statistics_anxiety persistence grade
self_efficacy 1.00 -0.07 0.06 -0.13
statistics_anxiety -0.07 1.00 0.00 -0.01
persistence 0.06 0.00 1.00 0.08
grade -0.13 -0.01 0.08 1.00
n= 473
P
self_efficacy statistics_anxiety persistence grade
self_efficacy 0.1096 0.1990 0.0065
statistics_anxiety 0.1096 0.9884 0.8736
persistence 0.1990 0.9884 0.0906
grade 0.0065 0.8736 0.0906 profile_data %>%
filter(mod2_profile == 3) %>%
select(self_efficacy, statistics_anxiety, persistence, grade) %>%
as.matrix() %>%
Hmisc::rcorr(type = "pearson") self_efficacy statistics_anxiety persistence grade
self_efficacy 1.00 0.09 -0.05 -0.16
statistics_anxiety 0.09 1.00 -0.06 -0.04
persistence -0.05 -0.06 1.00 0.00
grade -0.16 -0.04 0.00 1.00
n= 167
P
self_efficacy statistics_anxiety persistence grade
self_efficacy 0.2378 0.5281 0.0334
statistics_anxiety 0.2378 0.4291 0.5674
persistence 0.5281 0.4291 0.9829
grade 0.0334 0.5674 0.9829 profile_data %>%
select(self_efficacy, statistics_anxiety, persistence, grade) %>%
as.matrix() %>%
Hmisc::rcorr( type = "pearson") self_efficacy statistics_anxiety persistence grade
self_efficacy 1.00 -0.22 0.30 0.08
statistics_anxiety -0.22 1.00 -0.29 -0.16
persistence 0.30 -0.29 1.00 0.23
grade 0.08 -0.16 0.23 1.00
n= 854
P
self_efficacy statistics_anxiety persistence grade
self_efficacy 0.0000 0.0000 0.0214
statistics_anxiety 0.0000 0.0000 0.0000
persistence 0.0000 0.0000 0.0000
grade 0.0214 0.0000 0.0000 Profile Plot
estimates_table <- get_estimates(mod2) %>%
filter(Category == "Means") %>%
select("Parameter", "Estimate", "Class")
estimates_table$Class <- cut(estimates_table$Class, breaks = c(0,1,2,3), labels = c('1','2','3'))
estimates_table %>%
ggplot(aes(x = factor(Parameter, levels=c('statistics_anxiety','persistence','self_efficacy', 'grade' )), y = Estimate, group = Class, colour = Class)) + geom_point() + geom_line() +
scale_x_discrete(name="Variable",
labels=c("Statistics Anxiety", "Persistence", "Self-Efficacy", "Grade")) +
scale_y_continuous(name="Mean Value (Centred)",
limits=c(-1, 1),
n.breaks=10) +
labs(colour="Profile") +
theme_classic()